Graham Neubig, Yonatan Bisk, Hao Zhu
We lifted 3 functions out of this paper's own repositories and ran 2 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| CLAW-Lab/ToM | canonical | 2 of 3 |
| Function | Status | Where it lives |
|---|---|---|
| gen_game | Ran | CLAW-Lab/ToM/ibr_game/maml_speaker.py code served (permissive licence) · get_code("43ac615130f16ebb") |
| get_maml_args | Ran | CLAW-Lab/ToM/ibr_game/maml_speaker.py code served (permissive licence) · get_code("3304e04a7b24930a") |
| beam_search | Not yet run | CLAW-Lab/ToM/ibr_game/beam_search.py code served (permissive licence) · get_code("aa908768350f33fc") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
No man is an island. Humans communicate with a large community by coordinating with different interlocutors within short conversations. This ability has been understudied by the research on building neural communicative agents. We study the task of few-shot language coordination: agents quickly adapting to their conversational partners' language abilities. Different from current communicative agents trained with selfplay, we require the lead agent to coordinate with a population of agents with different linguistic abilities, quickly adapting to communicate with unseen agents in the population. This requires the ability to model the partner's beliefs, a vital component of human communication. Drawing inspiration from theory-of-mind (ToM; Premack & Woodruff ( 1978)), we study the effect of the speaker explicitly modeling the listeners' mental states. The speakers, as shown in our experiments, acquire the ability to predict the reactions of their partner, which helps it generate instructions that concisely express its communicative goal. We examine our hypothesis that the instructions generated with ToM modeling yield better communication performance in both a referential game and a language navigation task. Positive results from our experiments hint at the importance of explicitly modeling communication as a socio-pragmatic progress. Code can be found at https://github.com/CLAW-Lab/ToM.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2107.05697")
get_code_for_paper("2107.05697")
have("2107.05697")
Connect an agent — have() is free.